Data & Analytics

Capture, normalize, and report metrics across any domain with reusable dimensions, programmable formulas, and scalable reporting workflows.

Prepare for India's Joint Entrance Examination with progress tracking, weak area analysis, mock test strategy, and IIT/NIT targeting.

Avoid common Grafana mistakes — query pitfalls, variable templating, alerting traps, and provisioning gotchas.

Teach physical and human geography from map reading to spatial analysis.

Analyze football and soccer matches, squads, players, and training plans with tactical frameworks, scouting grids, and session blueprints.

Create, inspect, and edit Microsoft Excel workbooks and XLSX files with reliable formulas, dates, types, formatting, recalculation, and template preservation. Use when (1) the task is about Excel, `.xlsx`, `.xlsm`, `.xls`, `.csv`, or `.tsv`; (2) formulas, formatting, workbook structure, or compatibility matter; (3) the file must stay reliable after edits.

Work with data across the full lifecycle from extraction and cleaning to analysis, visualization, and reporting.

Data analysis and visualization. Query databases, generate reports, automate spreadsheets, and turn raw data into clear, actionable insights. Use when (1) you need to analyze, visualize, or explain data; (2) the user wants reports, dashboards, or metrics turned into a decision; (3) the work involves SQL, Python, spreadsheets, BI tools, or notebooks; (4) you need to compare segments, cohorts, funnels, experiments, or time periods; (5) the user explicitly installs or references the skill for th...

Model business performance, define KPIs, and turn data into decision-ready dashboards, briefings, and operating cadences for teams and executives.

Use when a skill isn't triggering as expected, before adding a new skill (to check for a name collision), during periodic cleanup of an accumulated skills directory, or when asked to review skill quality — checks frontmatter validity, description quality against Skill Discovery Optimization conventions, body size, and cross-scope name collisions.

Use before publishing documentation, merging a docs PR, or reporting a Markdown-heavy repo's navigation as complete — when you want ground-truth confirmation that internal links, heading anchors, and directory links resolve, without opening every file yourself.

Use when cutting a release, writing a CHANGELOG entry, or summarizing what changed since a tag — when the repo's commits follow (or mostly follow) Conventional Commits and a mechanically-accurate section breakdown beats a model's reading of the diff.

Execute Python code in a safe sandboxed environment via [inference.sh](https://inference.sh). Pre-installed: NumPy, Pandas, Matplotlib, requests, BeautifulSoup, Selenium, Playwright, MoviePy, Pillow, OpenCV, trimesh, and 100+ more libraries. Use for: data processing, web scraping, image manipulation, video creation, 3D model processing, PDF generation, API calls, automation scripts. Triggers: python, execute code, run script, web scraping, data analysis, image processing, video editing, 3D mo...

当用户提供数据文件（CSV / Excel / JSON / TSV）或表格数据，想要做分析、找洞察或要一份报告时使用——例如「分析数据」「做数据报告」「帮我看看这份数据」「这批订单数据说明什么」，以及销售 / 经营 / 运营数据复盘、探索性分析（EDA）、A/B 实验评估、趋势预测，或要一份可交互的 HTML 数据报告。不适用于：搭建 dashboard 应用、网页爬取、连接线上数据库。

<One-line description of when to use this skill. Keep it under 160 characters.>

Install or migrate BIRD 2/3 editor support and @birdcc/cli. Use for the BIRD2 LSP VS Code extension, the separate TextMate syntax extension or extension pack, VS Code forks, BIRD.nvim, BIRD.vim, manual Neovim LSP wiring, JetBrains TextMate bundles, birdcc CLI installation, offline VSIX setup, or migrations from BIRD2.nvim/BIRD2.vim. Route config diagnostics to bird-agent and GitHub Actions to birdcc-cicd.

Build or review GitHub Actions workflows for BIRD 2/3 projects using bird-chinese-community/setup-birdcc and @birdcc/cli. Use for pull-request lint/format/parse checks, BIRD2/BIRD3 matrices, BIRD_BIN, changed config files, pnpm/Turbo caching, submodule configs, action pinning, or .github/workflows changes. Route local config work to bird-agent and local editor/CLI installation to birdcc-installer.

Diagnose active BIRD daemon incidents across config, runtime, environment, sockets, logs, source, and tooling. Use when BIRD fails to start or reload, crashes, loses sessions/routes, behaves differently after lint passes, or when birdcc and bird -p disagree. Collect read-only evidence first, protect routing secrets, and route isolated config edits to bird-agent or pure implementation research to bird-source-explorer.

Trace BIRD routing-daemon behavior through the actual C source tree. Use for implementation questions, suspected upstream bugs, parser/keyword origins, filter instructions, protocol state machines, route attributes, birdc commands, stack traces, or BIRD 2 versus BIRD 3 source comparisons. Prefer a local checkout or exact upstream tag/commit and cite concrete files, functions, and revisions. Route config linting to bird-agent and active incidents to bird-troubleshooting.

Write, review, discover, lint, format, and validate BIRD 2/3 routing-daemon projects with the @birdcc toolchain. Use for bird.conf, bird2.conf, bird3.conf, bird6.conf, .bird/.bird2/.bird3 files, bird.config.json, birdcc.config.json, include graphs, BIRD filters and protocols, birdcc init/lint/fmt/lsp, or bird -p checks. Treat BIRD 1 as legacy and verify it with the actual BIRD 1 binary. Route editor and CLI installation to birdcc-installer, GitHub Actions to birdcc-cicd, runtime incidents to ...

Identify OWL enumeration classes and preserve their members in generated application models and diagrams. Use for owl:NamedIndividual discovery, rdf:type membership, enum deduplication, and regeneration checks.

Reports every score with its spread across folds or seeds, and says whether a gap between two numbers is bigger than that spread. Use when someone asks whether an improvement is real or just noise, or how confident to be that one model beats another. Use when two results are being called different or the same without a spread behind the claim.

Finds features that encode the answer — computed from the label, from the future, or contaminated across the train/test boundary. Use when a score looks too good to be true on the first try, such as AUC near 0.99 or R-squared near 1. Use when one feature dominates the importance ranking. Use when a feature was built from aggregates, neighbours, or anything derived from the thing being predicted.

Makes a notebook safe to rerun top to bottom and safe to read out of execution order. Use when a notebook only works if cells are run in a particular order, or its current state can no longer be trusted. Use when someone asks to clean up or tidy a notebook before sharing, reviewing, or handing it over.